BenchLeader
Trillion LabsOpen weightsReasoning modelCompare with another model

Tri-21B-Think

As of 16 Nov 2026, Tri-21B-Think by Trillion Labs is not yet ranked on the BenchLeader Index, which needs at least five independent results across two categories. Released 10 Feb 2026.

Key facts (as of 16 Nov 2026)

  • Tri-21B-Think was released on 10 Feb 2026 (Trillion Labs).

In detail. Tri-21B-Think is a Trillion Labs open-weights reasoning model, released 10 Feb 2026. It is not yet ranked: the index needs at least five independent results across two categories. Last measured 10 Feb 2026.stale: no new result in six months

Blended price
–
Output speed
–
First answer
–
Context
32k
via Artificial Analysis
Cost per task
–
Tokens per task
–
Released
10 Feb 2026
How it scores by categoryDashed line = average model (50). One step of 15 = one standard deviation.
  1. Agents & tools36
  2. Instruction following56
  3. Long context34

Get an email when Tri-21B-Think gets its first benchmark results

And when Trillion Labs ships a new model, plus the weekly review on Mondays.

Choose providers and emails

Benchmark results

See all LLM benchmarks. One column per reasoning effort. Rank is among every configuration of every model on that benchmark. Hover a score for the run it came from.

Metadata

BenchmarkthinkingSourceTrend
AA Openness Indexnot in index44.4#97Artificial Analysis

Reasoning

BenchmarkthinkingSourceTrend
GPQA Diamond (AA)not in index60.1%#383Artificial Analysis
Humanity's Last Exam (AA)not in index5.9%#433Artificial Analysis
CritPtnot in index0.3%#291Artificial Analysis

Agents & tools

BenchmarkthinkingSourceTrend
Terminal-Bench Hard2.3%#325Artificial Analysis
τ²-Bench Telecom (AA)not in index93.3%#43Artificial Analysis

Instruction following

BenchmarkthinkingSourceTrend
IFBench54.6%#152Artificial Analysis

Long context

BenchmarkthinkingSourceTrend
AA-LCR v1.121.7%#449Artificial Analysis

Composite

BenchmarkthinkingSourceTrend
AA Intelligence Index v4.3.2not in index9.6#403Artificial Analysis
AA Progress Index v1not in index197#429Artificial Analysis

New this month

See also

Questions people ask

Why does Tri-21B-Think have no BenchLeader Index score?
The index needs at least five independent results across at least two categories, and as of 16 Nov 2026 Tri-21B-Think does not have them yet. Launch-post scores are never used, so it is ranked once independent publishers have measured it.
When was Tri-21B-Think released?
Trillion Labs released Tri-21B-Think on 10 Feb 2026.

Data as of 16 Nov 2026. Compare with another model.

Cite as: BenchLeader, “Tri-21B-Think: benchmarks, pricing, speed and rank”, data as of 16 Nov 2026, https://www.benchleader.com/models/tri-21b.